Bioequivalence and Bioavailability Forum

Four Period Fully Replicated Crossover With Multiple Groups [General Statistics]

posted by Pankaj Bhangale – India, 2011-09-03 12:37 (5409 d 14:36 ago) – Posting: # 7332
Views: 7,172

Dear All,

Four period replicated crossover BE Study with 72 subjects. The subjects are divided in two groups with 36 Subject due to insufficient clinical capacity.

According to US-FDA Guidance for Industry, SAS code with ANOVA model to be used for the analysis of replicate crossover designs without groups is as follows.

proc mixed data=replicate;

class sequence period formulation subject;

model LCmax=sequence period formulation/ddfm=satterth;

random formulation/type=FA0(2) sub=subject G;

repeated/GRP=formulation sub=subject;

lsmeans formulation;

estimate 'Test vs Reference' formulation -1 1/CL alpha=0.10;

run;

Modified above SAS code with multiple groups is as follows:

proc mixed data=replicate;

class sequence period group formulation subject;

model LCmax=sequence period formulation group/ddfm=satterth;

random formulation/type=FA0(2) sub=subject G;

repeated/GRP=formulation sub=subject;

lsmeans formulation;

estimate 'Test vs Reference' formulation -1 1/CL alpha=0.10;

run;

Is it correct SAS code with ANOVA model for the analysis of replicate designs with multiple groups?

Regards,
Pankaj Bhangale

Complete thread:

Four Period Fully Replicated Crossover With Multiple GroupsPankaj Bhangale 2011-09-03 10:37
- Four Period Fully Replicated Crossover With Multiple Groups suchit_bhavsar 2014-05-28 08:38

Four Period Fully Replicated Crossover With Multiple Groups [General Sta­tis­tics]

Complete thread:

Four Period Fully Replicated Crossover With Multiple Groups [General Statistics]